@inproceedings{jahan-2020-team,
title = "Team Oulu at {S}em{E}val-2020 Task 12: Multilingual Identification of Offensive Language, Type and Target of {T}witter Post Using Translated Datasets",
author = "Jahan, Md Saroar",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.212",
doi = "10.18653/v1/2020.semeval-1.212",
pages = "1628--1637",
abstract = "With the proliferation of social media platforms, anonymous discussions together with easy online access, reports on offensive content have caused serious concern to both authorities and research communities. Although there is extensive research in identifying textual offensive language from online content, the dynamic discourse of social media content, as well as the emergence of new forms of offensive language, especially in a multilingual setting, calls for future research in the issue. In this work, we tackled Task A, B, and C of Offensive Language Challenge at SemEval2020. We handled offensive language in five languages: English, Greek, Danish, Arabic, and Turkish. Specifically, we pre-processed all provided datasets and developed an appropriate strategy to handle Tasks (A, B, {\&} C) for identifying the presence/absence, type and the target of offensive language in social media. For this purpose, we used OLID2019, OLID2020 datasets, and generated new datasets, which we made publicly available. We used the provided unsupervised machine learning implementation for automated annotated datasets and the online Google translation tools to create new datasets as well. We discussed the limitations and the success of our machine learning-based approach for all the five different languages. Our results for identifying offensive posts (Task A) yielded satisfactory accuracy of 0.92 for English, 0.81 for Danish, 0.84 for Turkish, 0.85 for Greek, and 0.89 for Arabic. For the type detection (Task B), the results are significantly higher (.87 accuracy) compared to target detection (Task C), which yields .81 accuracy. Moreover, after using automated Google translation, the overall efficiency improved by 2{\%} for Greek, Turkish, and Danish.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jahan-2020-team">
<titleInfo>
<title>Team Oulu at SemEval-2020 Task 12: Multilingual Identification of Offensive Language, Type and Target of Twitter Post Using Translated Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Saroar</namePart>
<namePart type="family">Jahan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the proliferation of social media platforms, anonymous discussions together with easy online access, reports on offensive content have caused serious concern to both authorities and research communities. Although there is extensive research in identifying textual offensive language from online content, the dynamic discourse of social media content, as well as the emergence of new forms of offensive language, especially in a multilingual setting, calls for future research in the issue. In this work, we tackled Task A, B, and C of Offensive Language Challenge at SemEval2020. We handled offensive language in five languages: English, Greek, Danish, Arabic, and Turkish. Specifically, we pre-processed all provided datasets and developed an appropriate strategy to handle Tasks (A, B, & C) for identifying the presence/absence, type and the target of offensive language in social media. For this purpose, we used OLID2019, OLID2020 datasets, and generated new datasets, which we made publicly available. We used the provided unsupervised machine learning implementation for automated annotated datasets and the online Google translation tools to create new datasets as well. We discussed the limitations and the success of our machine learning-based approach for all the five different languages. Our results for identifying offensive posts (Task A) yielded satisfactory accuracy of 0.92 for English, 0.81 for Danish, 0.84 for Turkish, 0.85 for Greek, and 0.89 for Arabic. For the type detection (Task B), the results are significantly higher (.87 accuracy) compared to target detection (Task C), which yields .81 accuracy. Moreover, after using automated Google translation, the overall efficiency improved by 2% for Greek, Turkish, and Danish.</abstract>
<identifier type="citekey">jahan-2020-team</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.212</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.212</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1628</start>
<end>1637</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team Oulu at SemEval-2020 Task 12: Multilingual Identification of Offensive Language, Type and Target of Twitter Post Using Translated Datasets
%A Jahan, Md Saroar
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F jahan-2020-team
%X With the proliferation of social media platforms, anonymous discussions together with easy online access, reports on offensive content have caused serious concern to both authorities and research communities. Although there is extensive research in identifying textual offensive language from online content, the dynamic discourse of social media content, as well as the emergence of new forms of offensive language, especially in a multilingual setting, calls for future research in the issue. In this work, we tackled Task A, B, and C of Offensive Language Challenge at SemEval2020. We handled offensive language in five languages: English, Greek, Danish, Arabic, and Turkish. Specifically, we pre-processed all provided datasets and developed an appropriate strategy to handle Tasks (A, B, & C) for identifying the presence/absence, type and the target of offensive language in social media. For this purpose, we used OLID2019, OLID2020 datasets, and generated new datasets, which we made publicly available. We used the provided unsupervised machine learning implementation for automated annotated datasets and the online Google translation tools to create new datasets as well. We discussed the limitations and the success of our machine learning-based approach for all the five different languages. Our results for identifying offensive posts (Task A) yielded satisfactory accuracy of 0.92 for English, 0.81 for Danish, 0.84 for Turkish, 0.85 for Greek, and 0.89 for Arabic. For the type detection (Task B), the results are significantly higher (.87 accuracy) compared to target detection (Task C), which yields .81 accuracy. Moreover, after using automated Google translation, the overall efficiency improved by 2% for Greek, Turkish, and Danish.
%R 10.18653/v1/2020.semeval-1.212
%U https://aclanthology.org/2020.semeval-1.212
%U https://doi.org/10.18653/v1/2020.semeval-1.212
%P 1628-1637
Markdown (Informal)
[Team Oulu at SemEval-2020 Task 12: Multilingual Identification of Offensive Language, Type and Target of Twitter Post Using Translated Datasets](https://aclanthology.org/2020.semeval-1.212) (Jahan, SemEval 2020)
ACL